Hello!

I am Simon Rendon Arango

Personal illustration

I build intelligent systems that turn messy data into clarity, combining machine learning, software design, and a bit of curiosity-driven engineering.

London, UK
Roles
Software Engineer · AI Engineer
Location
London
Connect
XLinkedInEmailGitHubDownload CV
About Me

Software and Machine Learning Engineer

Hi, I’m Simon Rendon Arango, a Software and Machine Learning Engineer passionate about building intelligent systems that turn complex data into actionable insights. I hold an MSc in Computing (Software Engineering) from Imperial College London and a BSc in Systems and Computing Engineering from Universidad de los Andes. My professional journey spans startups and fintech, where I’ve designed AI-driven KPI extraction modules, developed scalable backend services, and built user-facing products at companies like Untap, Glamper, and Nequi (Bancolombia).
I’m also a curious creator, constantly exploring new technologies and side projects at the intersection of AI, data, and design. I thrive in fast-paced, collaborative environments where ambitious ideas meet rigorous execution — and I’m always looking for opportunities to push the boundaries of what’s possible with software and machine learning.

Chat
Ask about my experience - Powered by RAG and LLM
Ask something like “What did Simon build at Untap?”
(
Experience

Professional Experience

Untap logo

Junior Software Engineer @ Untap

Nov 2024 – Present
Outcomes
90%+ KPI extraction accuracyAutomated testing coverage increasedFaster insight retrieval via Gemini
Tech Stack
ReactJavaScriptJavaVertexGeminiGCP
Impact
  • Developed and maintained software for private equity investment management using Java, Python, and JavaScript
  • Integrated Google Gemini for intelligent extraction and summarization of business‑critical information
  • Built an LLM‑based system to extract KPIs from financial reports with 90%+ accuracy
  • Implemented automated testing to ensure code quality, reliability, and maintainability across the development lifecycle
Glamper logo

Software Engineer @ Glamper

Mar 2023 – Sep 2023
Outcomes
LLM‑powered personalizationServerless backend on AWSImproved UX & engagement
Tech Stack
VueJavaScriptNuxtPythonAWS
Impact
  • Developed and maintained the Glamper web application using Vue.js and Nuxt.js, enhancing user experience and functionality
  • Integrated LLMs to provide personalized travel recommendations and improve customer engagement
  • Participated in code reviews and implemented best practices to ensure high-quality code and maintainability
  • Created a serverless backend using AWS Lambda and API Gateway to handle user requests and data processing
Bancolombia logo

Intern Software Engineer @ Bancolombia

Jul 2021 - Jan 2022
Outcomes
Automated incident trackingReduced deployment overhead
Tech Stack
PythonJavaScriptAWS
Impact
  • Developed internal AWS–Jira connectors to automate incident tracking, improving response time for infrastructure tickets.
  • Automated several cloud migration workflows, significantly reducing deployment overhead as Bancolombia transitioned to AWS.
Skills Overview

Focused Skills Hierarchy

Skills are grouped by category and then prioritized by importance. This makes it easy to scan what I rely on most versus what I use with solid working confidence.

Most ImportantStrongWorking Knowledge

Most Important At A Glance

14 core skills
Git
Other / DevOps
GitHub
Other / DevOps
JavaScript
Frontend
Jupyter
Machine Learning & Data
LLMs
Machine Learning & Data
Next.js
Frontend
Node.js
Backend & Cloud
NumPy
Machine Learning & Data
Pandas
Machine Learning & Data
Python
Backend & Cloud
RAG
Machine Learning & Data
React logo
React
Frontend
Tailwind CSS
Frontend
TypeScript
Frontend

Frontend

Most Important: 5Strong: 2Working Knowledge: 2
Most ImportantDeepest and most frequently used skills
5
JavaScriptExpert
Next.jsExpert
React logo
ReactExpert
Tailwind CSSExpert
TypeScriptExpert
StrongProduction-ready, used often
2
Framer MotionAdvanced
shadcn/uiAdvanced
Working KnowledgeComfortable and actively improving
2
Nuxt.jsProficient
VueProficient

Backend & Cloud

Most Important: 2Strong: 5Working Knowledge: 1
Most ImportantDeepest and most frequently used skills
2
Node.jsExpert
PythonExpert
StrongProduction-ready, used often
5
AWSAdvanced
DockerAdvanced
ExpressAdvanced
GCPAdvanced
JavaAdvanced
Working KnowledgeComfortable and actively improving
1
C++Proficient

Machine Learning & Data

Most Important: 5Strong: 6Working Knowledge: 1
Most ImportantDeepest and most frequently used skills
5
JupyterExpert
LLMsExpert
NumPyExpert
PandasExpert
RAGExpert
StrongProduction-ready, used often
6
Data VisualizationAdvanced
Deep LearningAdvanced
MCPAdvanced
Reinforcement LearningAdvanced
Scikit-learnAdvanced
TensorFlowAdvanced
Working KnowledgeComfortable and actively improving
1
PyTorchProficient

Other / DevOps

Most Important: 2Strong: 3Working Knowledge: 1
Most ImportantDeepest and most frequently used skills
2
GitExpert
GitHubExpert
StrongProduction-ready, used often
3
CI/CDAdvanced
DesignAdvanced
GitLabAdvanced
Working KnowledgeComfortable and actively improving
1
HPCProficient
Projects

Projects Worked On

Machine Learning – Predicting Formula 1 Results

Machine Learning – Predicting Formula 1 Results

Undergraduate thesis predicting race winners across seasons with ~93% accuracy.

93%+ accuracy in winner predictionPodium probability distribution modelingModel explainability (SHAP) for trustValidated against betting odds (profitable)
PythonTensorFlowScikit-learnPandas
Open Source
Performance Regression Detection in HPC (Nektar++)

Performance Regression Detection in HPC (Nektar++)

Master’s thesis: Deep learning anomaly detection on performance counters integrated into CI.

Regression triage time cut from days to <2 hoursAutomated anomaly detection in CICounter attribution for root cause analysis
PythonTensorFlowScikit-learnPandasNumPyHPCGitLab CIDeep LearningOpen Source
UNTAP – Financial Data Extraction Engine

UNTAP – Financial Data Extraction Engine

Fine-tuned LLM pipeline that extracts KPIs, targets and metrics from financial documents at 90%+ accuracy.

90%+ extraction accuracy via fine-tuning and prompt engineeringReduced client data ingestion time by over 80%Scalable across high volumes of diverse financial documents
JavaGCPReactLLMsFine-tuningPrompt Engineering
UNTAP – Investor Intelligence System

UNTAP – Investor Intelligence System

RAG pipeline and MCP server enabling natural language querying over portfolio investment data.

Natural language querying over live portfolio investment dataMCP server enabling agentic LLM workflows over internal toolsAI condition evaluator surfacing relevant deals against client priorities
JavaGCPBigQueryGeminiRAGMCPLLMsPython
EvalLens

EvalLens

Systematic LLM evaluation framework for making model quality measurable, reproducible, and actionable.

Reproducible, versioned LLM evaluation across model and prompt variantsCustom metric definitions beyond standard benchmark scoresCI/CD-ready — catches regressions before they reach production
PythonLLMsEvaluationRAGBackendCI/CD
Interactive Career Graph

Interactive Career Graph

Explorable knowledge graph of roles, education, tech and projects with dynamic layouts and deep linking.

Career represented as a typed relational graph, not a flat timelineMultiple dynamic layout modes with physics tuning and exportAccessible, deep-linkable, and shareable with URL state encoding
TypeScriptReactFramer MotionData VisState Encoding
ProjectWIP

Live Football Model (LFM)

Real-time probabilities, an embedding explorer, and a simulation toolkit that turns matches into living systems. I’m actively building it—come see the progress.

Live probabilitiesEmbedding explorerSimulation lab
State-of-the-art architecture
  • Streaming ingestion + feature store
  • Online inference with calibrated probabilities
  • Embeddings + vector search for similarity
  • Monte Carlo simulation engine
  • Real-time visualization layer
  • API-first design with SDKs
Visit LFMCurrently in progress
Model vs MarketLive · Embeddings · Sim
Education

Educational Background

Universidad de los Andes logo

Universidad de los Andes

Bachelor's Degree
Bachelor of Science in Systems and Computing Engineering
Bogotá, Colombia
Graduated:2023
Relevant Courses:
Data Structures, Algorithm design and analysis, Software Engineering, Mobile and Web Development, Software Architecture
Highlights:
  • Built a strong foundation in computer science, software development, and machine learning.
  • Completed hands-on projects including data analysis, algorithm design, and AI applications.
Imperial College London logo

Imperial College London

Master's Degree
Master of Science in Computing (Software Engineering)
London, United Kingdom
Graduated:Sep 2024
Relevant Courses:
Reinforcement Learning, Deep Learning, Software Engineering, Machine Learning, Natural Language Processing
Highlights:
  • Specialized in advanced software engineering principles, machine learning, and AI.
  • Conducted research and projects on scalable software systems and intelligent applications.
)

Lets build something great

Reach out for roles, collaborations, or interesting problems.